* Copyright (C) 1995-2005, Index Data ApS
* See the file LICENSE for details.
*
- * $Id: tsticonv.c,v 1.13 2006-01-29 21:59:13 adam Exp $
+ * $Id: tsticonv.c,v 1.17 2006-04-19 23:15:40 adam Exp $
*/
#if HAVE_CONFIG_H
yaz_iconv_close(cd);
}
}
+
+int utf8_check(unsigned c)
+{
+ if (sizeof(c) >= 4)
+ {
+ size_t r;
+ char src[4];
+ char dst[4];
+ char utf8buf[6];
+ char *inbuf = src;
+ size_t inbytesleft = 4;
+ char *outbuf = utf8buf;
+ size_t outbytesleft = sizeof(utf8buf);
+ int i;
+ yaz_iconv_t cd = yaz_iconv_open("UTF-8", "UCS4LE");
+ if (!cd)
+ return 0;
+ for (i = 0; i<4; i++)
+ src[i] = c >> (i*8);
+
+ r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ yaz_iconv_close(cd);
+
+ if (r == (size_t)(-1))
+ return 0;
+
+ cd = yaz_iconv_open("UCS4LE", "UTF-8");
+ if (!cd)
+ return 0;
+ inbytesleft = sizeof(utf8buf) - outbytesleft;
+ inbuf = utf8buf;
+
+ outbuf = dst;
+ outbytesleft = 4;
+
+ r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ if (r == (size_t)(-1))
+ return 0;
+
+ yaz_iconv_close(cd);
+
+ if (memcmp(src, dst, 4))
+ return 0;
+ }
+ return 1;
+}
+static int tst_convert(yaz_iconv_t cd, const char *buf, const char *cmpbuf)
+{
+ int ret = 0;
+ WRBUF b = wrbuf_alloc();
+ char outbuf[12];
+ size_t inbytesleft = strlen(buf);
+ const char *inp = buf;
+ while (inbytesleft)
+ {
+ size_t outbytesleft = sizeof(outbuf);
+ char *outp = outbuf;
+ size_t r = yaz_iconv(cd, (char**) &inp, &inbytesleft,
+ &outp, &outbytesleft);
+ if (r == (size_t) (-1))
+ {
+ int e = yaz_iconv_error(cd);
+ if (e != YAZ_ICONV_E2BIG)
+ break;
+ }
+ wrbuf_write(b, outbuf, outp - outbuf);
+ }
+ if (wrbuf_len(b) == strlen(cmpbuf)
+ && !memcmp(cmpbuf, wrbuf_buf(b), wrbuf_len(b)))
+ ret = 1;
+ else
+ yaz_log(YLOG_LOG, "GOT (%.*s)", wrbuf_len(b), wrbuf_buf(b));
+ wrbuf_free(b, 1);
+ return ret;
+}
+
+static void tst_conversion_marc8_to_latin1()
+{
+ yaz_iconv_t cd = yaz_iconv_open("ISO-8859-1", "MARC8");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours de math",
+ "Cours de math"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâe",
+ "Cours de mathé"));
+ YAZ_CHECK(tst_convert(cd, "12345678âe",
+ "12345678é"));
+ YAZ_CHECK(tst_convert(cd, "123456789âe",
+ "123456789é"));
+ YAZ_CHECK(tst_convert(cd, "1234567890âe",
+ "1234567890é"));
+ YAZ_CHECK(tst_convert(cd, "12345678901âe",
+ "12345678901é"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâem",
+ "Cours de mathém"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâematiques",
+ "Cours de mathématiques"));
+
+ yaz_iconv_close(cd);
+}
+
+static void tst_conversion_utf8_to_marc8()
+{
+ yaz_iconv_t cd = yaz_iconv_open("MARC8", "UTF-8");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours ", "Cours "));
+
+ /** Pure ASCII. 11 characters (sizeof(outbuf)-1) */
+ YAZ_CHECK(tst_convert(cd, "Cours de mat", "Cours de mat"));
+
+ /** Pure ASCII. 12 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"));
+
+ /** Pure ASCII. 13 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math.", "Cours de math."));
+
+ /** UPPERCASE SCANDINAVIAN O */
+ YAZ_CHECK(tst_convert(cd, "S\xc3\x98", "S\xa2"));
+
+ /** ARING */
+ YAZ_CHECK(tst_convert(cd, "A" "\xCC\x8A", "\xEA" "A"));
+
+ /** A MACRON + UMLAUT, DIAERESIS */
+ YAZ_CHECK(tst_convert(cd, "A" "\xCC\x84" "\xCC\x88",
+ "\xE5\xE8\x41"));
+
+ /* Ligature spanning two characters */
+ YAZ_CHECK(tst_convert(cd,
+ "\x74" "\xCD\xA1" "\x73", /* UTF-8 */
+ "\xEB\x74\xEC\x73")); /* MARC-8 */
+
+ /* Double title spanning two characters */
+ YAZ_CHECK(tst_convert(cd,
+ "\x74" "\xCD\xA0" "\x73", /* UTF-8 */
+ "\xFA\x74\xFB\x73")); /* MARC-8 */
+
+ /** Ideographic question mark (Unicode FF1F) */
+ YAZ_CHECK(tst_convert(cd,
+ "\xEF\xBC\x9F" "o", /* UTF-8 */
+ "\033(1" "\x21\x2B\x3B" "\033(B" "o" ));
+
+ yaz_iconv_close(cd);
+}
+
+
+static void tst_conversion_latin1_to_marc8()
+{
+ yaz_iconv_t cd = yaz_iconv_open("MARC8", "ISO-8859-1");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours ", "Cours "));
+
+ /** Pure ASCII. 11 characters (sizeof(outbuf)-1) */
+ YAZ_CHECK(tst_convert(cd, "Cours de mat", "Cours de mat"));
+
+ /** Pure ASCII. 12 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"));
+
+ /** Pure ASCII. 13 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math.", "Cours de math."));
+
+ /** UPPERCASE SCANDINAVIAN O */
+ YAZ_CHECK(tst_convert(cd, "SØ", "S\xa2"));
+
+ yaz_iconv_close(cd);
+}
+
int main (int argc, char **argv)
{
YAZ_CHECK_INIT(argc, argv);
+
+ tst_conversion_marc8_to_latin1();
+
+ tst_conversion_utf8_to_marc8();
+
+ tst_conversion_latin1_to_marc8();
+
+ YAZ_CHECK(utf8_check(3));
+ YAZ_CHECK(utf8_check(127));
+ YAZ_CHECK(utf8_check(128));
+ YAZ_CHECK(utf8_check(255));
+ YAZ_CHECK(utf8_check(256));
+ YAZ_CHECK(utf8_check(900));
+ YAZ_CHECK(utf8_check(1000));
+ YAZ_CHECK(utf8_check(10000));
+ YAZ_CHECK(utf8_check(100000));
+ YAZ_CHECK(utf8_check(1000000));
+ YAZ_CHECK(utf8_check(10000000));
+ YAZ_CHECK(utf8_check(100000000));
+
dconvert(1, "UTF-8");
dconvert(1, "ISO-8859-1");
dconvert(1, "UCS4");
tst_marc8_to_iso_8859_1();
tst_marc8_to_ucs4b();
tst_ucs4b_to_utf8();
+
YAZ_CHECK_TERM;
}
/*